Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instrument, how, normally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ję
    0.47
    lich
    0.44
    ipher
    0.43
     disguise
    0.43
     chemist
    0.42
     પહે
    0.41
    ح
    0.41
     cible
    0.41
     संधि
    0.41
    बद्दल
    0.41
    POSITIVE LOGITS
     சுமார்
    0.48
    ৫
    0.48
     ಗೋ
    0.47
    湾
    0.47
    scores
    0.45
     ዋና
    0.45
    シティ
    0.45
    itä
    0.44
    sinx
    0.44
    pageY
    0.44
    Act Density 0.001%

    No Known Activations